Firecrawl MCP Server is a Model Context Protocol server implementation that provides web scraping capabilities, including crawling, content extraction, and cloud browser automation.
From the registry: MCP server for Firecrawl web scraping, structured data extraction and web search integration.

Please install the `firecrawl-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Firecrawl API key** — Get an API key from Firecrawl dashboard (https://www.firecrawl.dev/app/api-keys)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","firecrawl-mcp"]
- required environment variables:
- `FIRECRAWL_API_KEY`: Firecrawl API key (required for cloud API) (example: `<your-firecrawl-api-key>`)
- optional environment variables:
- `FIRECRAWL_API_URL`: Custom API endpoint for self-hosted instances (example: `<your-firecrawl-url>`)
- `FIRECRAWL_RETRY_MAX_ATTEMPTS`: Maximum retry attempts (example: `3`)
- `FIRECRAWL_RETRY_INITIAL_DELAY`: Initial retry delay in milliseconds (example: `1000`)
- `FIRECRAWL_RETRY_MAX_DELAY`: Max retry delay in milliseconds (example: `10000`)
- `FIRECRAWL_RETRY_BACKOFF_FACTOR`: Exponential backoff multiplier (example: `2`)
- `FIRECRAWL_CREDIT_WARNING_THRESHOLD`: Credit warning threshold (example: `1000`)
- `FIRECRAWL_CREDIT_CRITICAL_THRESHOLD`: Credit critical threshold (example: `100`)
- `HTTP_STREAMABLE_SERVER`: Set to 'true' to run as local Streamable HTTP instead of stdio (example: `true`)
Note: Also supports Streamable HTTP local mode at http://localhost:3000/mcp via HTTP_STREAMABLE_SERVER=true.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.FIRECRAWL_API_KEYrequiredYour Firecrawl API key, required for using the cloud API.AI-powered browser automation — navigate, click, fill forms, and extract data from any website.